Login / Signup

A Conceptual Architecture for Deep-learning-based Video-Objects Retrieving System.

Dinh-Lam PhamViet-Vu VuByeongnam YoonKyoungsook KimKwanghoon Pio Kim
Published in: ICACT (2022)
Keyphrases
  • deep learning
  • video objects
  • mental models
  • unsupervised learning
  • weakly supervised
  • machine learning
  • video sequences
  • compressed domain
  • computer vision
  • learning algorithm
  • three dimensional
  • feature extraction